OpenProject MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@OpenProject MCP Server show me the tasks ready for AI development"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
OpenProject MCP Server
MCP (Model Context Protocol) сервер для интеграции OpenProject с AI IDE, такими как Cursor.
Возможности
get_ai_tasks — получение списка задач, готовых к разработке AI
Возвращает задачи из колонок "Баги" и "Готово к разработке"
Фильтрует только задачи с флагом
ai_dev = trueВозвращает: id, url, subject, description, type, status, priority, assignee
get_task — получение детальной информации о задаче по ID
Related MCP server: EasyProject MCP Server
Установка
1. Клонирование и установка зависимостей
cd /root/repos/openproject_mcp
pip install -e .2. Настройка
Создайте файл .env на основе .env.example:
cp .env.example .envОтредактируйте .env:
OPENPROJECT_URL=openproject_api_url
OPENPROJECT_API_KEY=your_api_key_here3. Настройка Cursor
Добавьте в конфигурацию MCP серверов Cursor (~/.cursor/mcp.json).
Важно: После pip install -e . команда openproject-mcp становится доступна в PATH.
Вариант A: После установки через pip (рекомендуется)
{
"mcpServers": {
"openproject": {
"command": "openproject-mcp",
"env": {
"OPENPROJECT_URL": "openproject_api_url",
"OPENPROJECT_API_KEY": "your_api_key_here"
}
}
}
}Вариант B: Без установки (указать путь к Python)
{
"mcpServers": {
"openproject": {
"command": "python",
"args": ["-m", "openproject_mcp.server"],
"cwd": "/path/to/openproject_mcp/src",
"env": {
"OPENPROJECT_URL": "openproject_api_url",
"OPENPROJECT_API_KEY": "your_api_key_here"
}
}
}
}Вариант C: Через uv/uvx
{
"mcpServers": {
"openproject": {
"command": "uvx",
"args": ["--from", "/path/to/openproject_mcp", "openproject-mcp"],
"env": {
"OPENPROJECT_URL": "openproject_api_url",
"OPENPROJECT_API_KEY": "your_api_key_here"
}
}
}
}Использование
После настройки в Cursor будут доступны инструменты:
Получить задачи для AI
Используй инструмент get_ai_tasks чтобы получить список задач готовых к разработкеПолучить конкретную задачу
Используй инструмент get_task с task_id=2243 чтобы получить детали задачиКонфигурация
Переменная | Описание | По умолчанию |
| URL OpenProject |
|
| API ключ | - |
| ID query колонки "Баги" |
|
| ID query колонки "Готово к разработке" |
|
| Имя кастомного поля ai_dev |
|
Получение API ключа
Войдите в OpenProject
Перейдите в My Account → Access tokens
Создайте новый API токен
Скопируйте токен в конфигурацию
Разработка
# Установка в режиме разработки
pip install -e ".[dev]"
# Запуск сервера напрямую
python -m openproject_mcp.serverЛицензия
MIT
Available Tools
2 toolsget_ai_tasksA
Get list of tasks ready for AI development from OpenProject. Returns tasks from 'Баги' and 'Готово к разработке' columns that have ai_dev flag set to true. Each task includes: id, url, subject, description, type, status, priority, assignee.
Inputs: no named parameters.
get_taskB
Get detailed information about a specific task by its ID. Returns full task details including description, status, assignee, etc.
Inputs: task_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one retrieves a single task by ID, the other lists filtered tasks based on specific criteria. No overlap in functionality.
Both tool names follow a consistent 'get_noun' snake_case pattern, making them predictable and easy to understand.
With only two tools for a project management server, the count is too low. A typical server for this domain would require additional tools for CRUD operations and broader querying.
The tool surface is severely incomplete: it lacks any create, update, or delete operations, and fails to support common workflows like listing all tasks or searching by other criteria.
Maintenance
Related MCP Connectors
Open your team's project from the AI you use: read and write its brief, documents, tasks and notes.
Manage Loom projects, tasks, bugs, defects, clients and phases from AI assistants
Bring meeting decisions, tasks and user stories into your AI editor (Claude, Cursor, Copilot).
Task management for people and AI agents, with scoped OAuth access to issues, projects, and docs.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to manage projects through OpenProject's API, providing complete project management capabilities including work packages, tasks, and team collaboration features.-
- AlicenseNot gradedqualityDmaintenanceIntegrates with EasyProject API to manage projects, tasks, users, time tracking, and reporting via MCP protocol in editors like Cursor AI.7 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables LLM applications to interact with OpenProject for project management, work package tracking, and task creation.91MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to access and manage OpenProject projects, work packages, attachments, time tracking, wiki, and users via the OpenProject API v3.-